Expectation maximization transfer learning and its application for bionic hand prostheses
This addresses robustness issues in bionic hand prostheses for users, though it is incremental as it builds on existing transfer learning methods.
The paper tackled the problem of data distribution shifts in bionic hand prostheses by proposing a novel expectation maximization algorithm for transfer learning, which improved classification accuracy significantly and outperformed baselines when few data or classes were available in the target domain.
Machine learning models in practical settings are typically confronted with changes to the distribution of the incoming data. Such changes can severely affect the model performance, leading for example to misclassifications of data. This is particularly apparent in the domain of bionic hand prostheses, where machine learning models promise faster and more intuitive user interfaces, but are hindered by their lack of robustness to everyday disturbances, such as electrode shifts. One way to address changes in the data distribution is transfer learning, that is, to transfer the disturbed data to a space where the original model is applicable again. In this contribution, we propose a novel expectation maximization algorithm to learn linear transformations that maximize the likelihood of disturbed data after the transformation. We also show that this approach generalizes to discriminative models, in particular learning vector quantization models. In our evaluation on data from the bionic prostheses domain we demonstrate that our approach can learn a transformation which improves classification accuracy significantly and outperforms all tested baselines, if few data or few classes are available in the target domain.